A new Graphics Processing Unit (GPU)-base machine learning algorithm develop by researchers at the Indian Institute of Science (IISc) can help scientists better understand and predict connectivity between different regions of the brain.
The algorithm, calls as Regularized, Accelerated, Linear Fascicle Evaluation, or ReAl-LiFE, can rapidly analyse the enormous amounts of data generate from diffusion Magnetic Resonance Imaging (dMRI) scans of the human brain.
Using ReAL-LiFE, the team was able to evaluate dMRI data over 150 times faster than existing state-of-the-art algorithms, according to an IISc press release.
Devarajan Sridharan, Associate Professor at the Centre for Neuroscience (CNS), IISc, and corresponding author of the study publish in the journal Nature Computational Science. Said :
Millions of neurons fire in the brain every second, generating electrical pulses that travel across neuronal networks from one point in the brain to another through connecting cables or “axons”.
These connections are essential for computations that the brain performs.
Varsha Sreenivasan, PhD student at CNS and first author of the study Said :
So conventional approaches to study brain connectivity typically use animal models, and are invasive. dMRI scans, on the other hand, provide a non-invasive method to study brain connectivity in humans.
The cables (axons) that connect different areas of the brain are its information highways.
Because bundles of axons are shape like tubes, water molecules move through them, along their length, in a direct manner.
dMRI allows scientists to track this movement, in order to create a comprehensive map of the network of fibres across the brain, called a connectome.
It is not straightforward to pinpoint these connectomes.
The data obtain from the scans only provide the net flow of water molecules at each point in the brain, the release note.
Varsha Sreenivasan Explains :
To identify these networks accurately, conventional algorithms closely match the predicted dMRI signal from the inferred connectome with the observe dMRI signal.
Scientists had previously develop an algorithm call as LiFE (Linear Fascicle Evaluation) to carry out this optimisation, but one of its challenges was that it work on traditional Central Processing Units (CPUs), which made the computation time-consuming.
In the new study, Varsha Sreenivasan’s team tweak their algorithm to cut down the computational effort involved in many ways, including removing redundant connections, thereby improving upon LiFE’s performance significantly.
To speed up the algorithm further, the team also redesign it to work on specialise electronic chips, the kind found in high-end gaming computers – called Graphics Processing Units (GPUs), which help them analyse data at speeds 100-150 times faster than previous approaches.
This improve algorithm, ReAl-LiFE, was also able to predict how a human test subject would behave or carry out a specific task.
In other words, using the connection strengths estimate by the algorithm for each individual, the team was able to explain variations in behavioural and cognitive test scores across a group of 200 participants.
Such analysis can have medical applications too.
Varsha Sreenivasan Said :
For example, using the obtaine connectomes, the team hopes to be able to identify early signs of aging or deterioration of brain function before they manifest behaviourally in Alzheimer’s patients.
Varsha Sreenivasan Said :
Varsha Sreenivasan adds that their GPU-base implementation is very general, and can be used to tackle optimisation problems in many other fields as well.